© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52869
    Prev
    Next
    INDEX
    Explanations

    call 988 or 111

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     спі
    0.45
     Navarro
    0.42
     наві
    0.40
    琉
    0.38
    Wiley
    0.38
     Assets
    0.38
     удовле
    0.38
     Wiley
    0.37
    升
    0.37
    陞
    0.37
    POSITIVE LOGITS
    fez
    0.41
    ട്ടുള്ള
    0.40
     diast
    0.39
     framebuffer
    0.39
     terrible
    0.38
     diameters
    0.38
     sogno
    0.38
     axes
    0.37
     matplotlib
    0.36
    SaveFolder
    0.36
    Activations Density 0.001%

    No Known Activations